Disk Traces Research Articles

Polling Sanitization to Balance I/O Latency and Data Security of High-density SSDs

Sanitization is an effective approach for ensuring data security through scrubbing invalid but sensitive data pages, with the cost of impacts on storage performance due to moving out valid pages from the sanitization-required wordline, which is a logical read/write unit and consists of multiple pages in high-density SSDs. To minimize the impacts on I/O latency and data security, this article proposes a polling-based scheduling approach for data sanitization in high-density SSDs. Our method polls a specific SSD channel for completing data sanitization at the block granularity, meanwhile other channels can still service I/O requests. Furthermore, our method assigns a low priority to the blocks that are more likely to have future adjacent page invalidations inside sanitization-required wordlines, while selecting the sanitization block, to minimize the negative impacts of moving valid pages. Through a series of emulation experiments on several disk traces of real-world applications, we show that our proposal can decrease the negative effects of data sanitization in terms of the risk-performance index, which is a united time metric of I/O responsiveness and the unsafe time interval, by 16.34% , on average, compared to related sanitization methods.

Adaptive Switch on Wear Leveling for Enhancing I/O Latency and Lifetime of High-Density SSDs

NAND flash-based high-density solid-state drives (SSDs) commonly have limited write endurance, as a single block becomes unavailable after a finite number of program/erase cycles. The (static) wear leveling algorithms migrate cold data to more worn blocks for yielding an even distribution of wears in SSDs. However, migrating cold data must delay normal I/O processing, and unnecessary wear leveling operations may damage SSD endurance as each operation causes a program/erase cycle. This article proposes an adaptive switch on wear leveling (called ASWL), to boost I/O performance and lifetime for high-density SSDs. The basic idea of ASWL is to adaptively switch the threshold function for intelligently triggering wear leveling operations at different stages of SSD lifetime. To this end, we build a mathematical model determining the wear leveling threshold condition with a dynamic manner, by considering the real-time factors of I/O intensity and the wear difference of SSD blocks. Through a series of emulation experiments on several realistic disk traces, we show that the proposed ASWL mechanism can not only greatly improve I/O performance but also noticeably extend the lifetime of high-density SSDs, in contrast to existing wear leveling methods.

Distributions of gas and small and large grains in the LkHα 330 disk trace a young planetary system,

Planets that are forming around young stars are expected to leave clear imprints in the distribution of the gas and dust of their parental protoplanetary disks. In this paper, we present new scattered light and millimeter observations of the protoplanetary disk around LkHα 330, using SPHERE/VLT and ALMA, respectively. The scattered-light SPHERE observations reveal an asymmetric ring at around 45 au from the star in addition to two spiral arms with similar radial launching points at around 90 au. The millimeter observations from ALMA (resolution of 0.06″ × 0.04″) mainly show an asymmetric ring located at 110 au from the star. In addition to this asymmetry, there are two faint symmetric rings at 60 au and 200 au. The 12CO, 13CO, and C18O lines seem to be less abundant in the inner disk (these observations have a resolution of 0.16″ × 0.11″). The 13CO peaks at a location similar to the inner ring observed with SPHERE, suggesting that this line is optically thick and traces variations of disk temperature instead of gas surface-density variations, while the C18O peaks slightly further away at around 60 au. We compare our observations with hydrodynamical simulations that include gas and dust evolution, and conclude that a 10 MJup mass planet at 60 au and in an eccentric orbit (e = 0.1) can qualitatively explain most of the observed structures. A planet in a circular orbit leads to a much narrower concentration in the millimeter emission, while a planet in a more eccentric orbit leads to a very eccentric cavity as well. In addition, the outer spiral arm launched by the planet changes its pitch angle along the spiral due to the eccentricity and when it interacts with the vortex, potentially appearing in observations as two distinct spirals. Our observations and models show that LkHα 330 is an interesting target to search for (eccentric-) planets while they are still embedded in their parental disk, making it an excellent candidate for studies on planet-disk interaction.

Read Refresh Scheduling and Data Reallocation against Read Disturb in SSDs

Read disturb is a circuit-level noise in flash-based Solid-State Drives (SSDs), induced by intensive read requests, which may result in unexpected read errors. The approach of read refresh (RR) is commonly adopted to mitigate its negative effects by unconditionally migrating all valid data pages in the RR block to another new block. However, routine RR operations greatly impact the I/O responsiveness of SSDs, because the processing on normal I/O requests must be blocked at the same time. To further reduce the negative effects of read refresh, this article proposes a read refresh scheduling and data reallocation method to deal with two primary issues with respect to an RR operation, including where to place data pages and when to trigger page migrations. Specifically, we first construct a data reallocation model to match the data pages in the RR block and the destination blocks for addressing the issue of where to place the data. The model considers not only the read hotness of pages in the RR block, but also the accumulated read counts of the destination blocks. Moreover, for addressing the issue of when to trigger data migrations, we build a timing decision model to determine the time points for completing page migrations by considering the factors of the intensity of I/Os and the disturb situation on the RR block. Through a series of simulation experiments based on several realistic disk traces, we illustrate that the proposed RR scheduling and data reallocation mechanism can noticeably reduce the read errors by more than 10.3% , on average, and the long-tail latency by between 43.9% and 64.0% at the 99.99th percentile, in contrast to state-of-the-art methods.

Low I/O Intensity-aware Partial GC Scheduling to Reduce Long-tail Latency in SSDs

This article proposes a low I/O intensity-aware scheduling scheme on garbage collection (GC) in SSDs for minimizing the I/O long-tail latency to ensure I/O responsiveness. The basic idea is to assemble partial GC operations by referring to several determinable factors (e.g., I/O characteristics) and dispatch them to be processed together in idle time slots of I/O processing. To this end, it first makes use of Fourier transform to explore the time slots having relative sparse I/O requests for conducting time-consuming GC operations, as the number of affected I/O requests can be limited. After that, it constructs a mathematical model to further figure out the types and quantities of partial GC operations, which are supposed to be dealt with in the explored idle time slots, by taking the factors of I/O intensity, read/write ratio, and the SSD use state into consideration. Through a series of simulation experiments based on several realistic disk traces, we illustrate that the proposed GC scheduling mechanism can noticeably reduce the long-tail latency by between 5.5% and 232.3% at the 99.99th percentile, in contrast to state-of-the-art methods.

Patch-Based Data Management for Dual-Copy Buffers in RAID-Enabled SSDs

While a dual-copy redundant array of independent disk (RAID) buffering can remove single point of failure in the buffer of RAID-enabled solid-state drives (SSDs), it loses a half of buffer space efficiency as a result. This article introduces a patch-based data management scheme for dual-copy buffers in RAID-enabled SSDs, for better improving buffer use efficiency. Different from conventional methods that caches data/parity chunks in the RAID buffer, it caches the modified portions of data chunks (called data patches) and then employs a cost-evaluation model to direct patch data replacement. Besides, in order to correctly respond to applications' read/write requests, we design the patch-based read/write mode by taking the original dirty data chunks and relevant up-to-date patches into account. Through a series of simulation tests on several realistic disk traces, we illustrate that patch-based data management can work for RAID-enabled SSDs to enhance buffer use efficiency, and then yield better I/O performance. Especially, our proposal can noticeably reduce the I/O latency by 39.1% and the number of block erases by 3.9% on average, in contrast to state-of-the-art approaches.

Mitigating Negative Impacts of Read Disturb in SSDs

Read disturb is a circuit-level noise in solid-state drives (SSDs), which may corrupt existing data in SSD blocks and then cause high read error rate and longer read latency. The approach of read refresh is commonly used to avoid read disturb errors by periodically migrating the hot read data to other free blocks, but it places considerable negative impacts on I/O (Input/Output) responsiveness. This article proposes scheduling approaches on write data and read refresh operations, to mitigate the negative effects caused by read disturb. To be specific, we first construct a model to classify SSD blocks into two categories according to the estimated read error rate by referring to the factors of block’s P/E (Program/Erase) cycle and the accumulated read count to the block. Then, the data being intensively read will be redirected to the block having a small read error rate, as it is not sensitive to read disturb even though the data will be heavily requested. Moreover, we take advantage of reinforcement learning to predict the idle interval between two I/O requests for purposely conducting (partial) read refresh operations. As a result, it is able to minimize negative impacts toward subsequent incoming I/O requests and to ensure I/O responsiveness. Through a series of emulation tests on several realistic disk traces, we demonstrate that the proposed mechanisms can noticeably yield performance improvements on the metrics of read error rate and I/O latency.

Frequent Pattern-Based Mapping at Flash Translation Layer of Solid-State Drives

In order to reduce the overhead of garbage collection, as well as yield an even erasure distribution of blocks in solid-state drives (SSDs), this paper proposes a mapping approach at flash translation layer (FTL) of the SSD devices. To be specific, it first analyzes certain I/O requests, for mining frequent item sets of logical sector numbers, to direct scheduling the write requests. After that, we map the requests belonging to the same frequent itemset, to the SSD blocks having a relative small erasure count. That is to say, these requests are supposed to be flushed onto the same SSD blocks when they have been ejected from the cache. As a result, the data on the same block are mostly like to be rewritten together in the near future, so that the overhead of garbage collection can be significantly cut down. Furthermore, it is able to yield a uniform erasure distribution among all blocks of SSDs even without wear-leveling optimization, to purposely extend the lifetime of the SSDs. Through a series of simulation experiments with a number of write-intensive disk traces of real-world applications, we conclude that this newly proposed mechanism does work, as expected.

Securing Coding-Based Cloud Storage Against Pollution Attacks

The widespread diffusion of distributed and cloud storage solutions has changed dramatically the way users, system designers, and service providers manage their data. Outsourcing data on remote storage provides indeed many advantages in terms of both capital and operational costs. The security of data outsourced to the cloud, however, still represents one of the major concerns for all stakeholders. Pollution attacks, whereby a set of malicious entities attempt to corrupt stored data, are one of the many risks that affect cloud data security. In this paper we deal with pollution attacks in coding-based block-level cloud storage systems, i.e., systems that use linear codes to fragment, encode, and disperse virtual disk sectors across a set of storage nodes to achieve desired levels of redundancy, and to improve reliability and availability without sacrificing performance. Unfortunately, the effects of a pollution attack on linear coding can be disastrous, since a single polluted fragment can propagate pervasively in the decoding phase, thus hampering the whole sector. In this work we show that, using rateless codes, we can design an early pollution detection algorithm able to spot the presence of an attack while fetching the data from cloud storage during the normal disk reading operations. The alarm triggers a procedure that locates the polluting nodes using the proposed detection mechanism along with statistical inference. The performance of the proposed solution is analyzed under several aspects using both analytical modelling and accurate simulation using real disk traces. Our results show that the proposed approach is very robust and is able to effectively isolate the polluters, even in harsh conditions, provided that enough data redundancy is used.

DiskAccel

Disk traces are typically used to analyze real-life workloads and for replay-based evaluations. This approach benefits from capturing important details such as varying behavior patterns, bursty activity, and diurnal patterns of system activity, which are often missing from the behavior of workload synthesis tools. However, accurate capture of such details requires recording traces containing long durations of system activity, which are difficult to use for replay-based evaluation. One way of solving the problem of long storage trace duration is the use of disk simulators. While publicly available disk simulators can greatly accelerate experiments, they have not kept up with technological innovations in the field. The variety, complexity, and opaque nature of storage hardware make it very difficult to implement accurate simulators. The alternative, replaying the whole traces on real hardware, suffers from either long run-time or required manual reduction of experimental time, potentially at the cost of reduced accuracy. On the other hand, burstiness, auto-correlation, and complex spatio-temporal properties of storage workloads make the known methods of sampling workload traces less effective. In this paper, we present a methodology called DiskAccel to efficiently select key intervals of a trace as representatives and to replay them to estimate the response time of the whole workload. Our methodology extracts a variety of spatial and temporal features from each interval and uses efficient data mining techniques to select the representative intervals. To verify the proposed methodology, we have implemented a tool capable of running whole traces or selective intervals on real hardware, warming up hardware state in an accelerated manner, and emulating request causality while minimizing request inter-arrival time error. Based on our experiments, DiskAccel manages to speed up disk replay by more than two orders of magnitude, while keeping average estimation error at 7.6%.

Adaptive Wear-Leveling in Flash-Based Memory

The paper presents an adaptive wear-leveling scheme based on several wear-thresholds in different periods. The basic idea behind this scheme is that blocks can have different wear-out speeds and the wear-leveling mechanism does not conduct data migration until the erasure counts of some hot blocks hit a threshold. Through a series of emulation experiments based on several realistic disk traces, we show that the proposed wear-leveling mechanism can reduce total erasure counts and yield uniform erasure counts among all blocks at the late lifetime of the storage devices. As a result, not only can the performance of storage systems be advanced, the lifespan of the flash-based memory can also be extended to a certain degree.

Design and Evaluation of a New Approach to RAID-0 Scaling

Scaling up a RAID-0 volume with added disks can increase its storage capacity and I/O bandwidth simultaneously. For preserving a round-robin data distribution, existing scaling approaches require all the data to be migrated. Such large data migration results in a long redistribution time as well as a negative impact on application performance. In this article, we present a new approach to RAID-0 scaling called FastScale. First, FastScale minimizes data migration, while maintaining a uniform data distribution. It moves only enough data blocks from old disks to fill an appropriate fraction of new disks. Second, FastScale optimizes data migration with access aggregation and lazy checkpoint. Access aggregation enables data migration to have a larger throughput due to a decrement of disk seeks. Lazy checkpoint minimizes the number of metadata writes without compromising data consistency. Using several real system disk traces, we evaluate the performance of FastScale through comparison with SLAS, one of the most efficient existing scaling approaches. The experiments show that FastScale can reduce redistribution time by up to 86.06% with smaller application I/O latencies. The experiments also illustrate that the performance of RAID-0 scaled using FastScale is almost identical to, or even better than, that of the round-robin RAID-0.

TPC-E vs. TPC-C

TPC-E is a new OLTP benchmark recently approved by the Transaction Processing Performance Council (TPC). In this paper, we compare TPC-E with the familiar TPCC benchmark in order to understand the behavior of the new TPC-E benchmark. In particular, we compare the I/O access patterns of the two benchmarks by analyzing two OLTP disk traces. We find that (i) TPC-E is more read intensive with a 9.7:1 I/O read to write ratio, while TPC-C sees a 1.9:1 read-to-write ratio; and (ii) although TPC-E uses pseudo-realistic data, TPC-E's I/O access pattern is as random as TPC-C. The latter suggests that like TPC-C, TPC-E can benefit from SSDs, which have superior random I/O support. To verify this, we replay both disk traces on an Intel X25-E SSD and see dramatic improvements for both TPC-C and TPC-E.

Conserving energy in real-time storage systems with I/O burstiness

Energy conservation has become a critical problem for real-time embedded storage systems. Although a variety of approaches for reducing energy consumption have been extensively studied, energy conservation for real-time embedded storage systems is still an open problem. In this article, we propose an energy management strategy, I/O Burstiness for Energy Conservation (IBEC), exploiting the burstiness of real-time embedded storage systems applications. Our approach aims at combining the IBEC energy-management strategy with a Linux-based disk block-scheduling mechanism to conserve the energy of storage systems. Extensive experiments are conducted involving a number of synthetic disk traces as well as real-world data-intensive traces. To evaluate the energy efficiency of IBEC, we compare the performance of IBEC against three existing strategies, namely, PA-EDF, DP-EDF, and EDF. Compared with the alternative strategies, IBEC reduces the power consumption of real-time embedded disks system by up to 60%.

The disk emission in single peaked lines for 12 AGNs

The disk emission in the single peaked Broad Emission Lines (BELs) of Active Galactic Nuclei (AGNs) is difficult to detect. In order to find the disk traces in BELs the line profiles were simulated by the simplified model consisting of two components: accretion disk and surrounding spherical region with isotropic velocities of clouds. The measurements of simulated profiles were compared with the measurements of observed single-peaked H? and H? profiles of 12 AGNs, that had been previously confirmed to show the accretion disk presence in the X domain. The results are in agreement with previous investigations.

Distances to Galactic High‐Velocity Clouds. I. Cohen Stream, Complex GCP, Cloud g1

The high- and intermediate-velocity interstellar clouds (HVCs/IVCs) are tracers of energetic processes in and around the Milky Way. Clouds with near-solar metallicity about 1 kpc above the disk trace the circulation of material between disk and halo (the Galactic fountain). The Magellanic Stream consists of gas tidally extracted from the SMC, tracing the dark matter potential of the Milky Way. Several other HVCs have low metallicity and appear to trace the continuing accretion of infalling intergalactic gas. These assertions are supported by the metallicities (0.1 to 1 solar) measured for about 10 clouds in the past decade. Direct measurements of distances to HVCs have remained elusive, however. In this paper we present four new distance brackets, using VLT observations of interstellar Ca II H and K absorption toward distant Galactic halo stars. We derive distance brackets of 5.0 to 11.7 kpc for the Cohen Stream (likely to be an infalling low-metallicity cloud), 9.8 to 15.1 kpc for Complex GCP (also known as the Smith Cloud or HVC 40–15+100 and with still unknown origin), 1.0 to 2.7 kpc for an IVC that appears associated with the return flow of the fountain in the Perseus arm, and 1.8 to 3.8 kpc for cloud g1, which appears to be in the outflow phase of the fountain. Our measurements further demonstrate that the Milky Way is accreting substantial amounts of gaseous material, which influences the Galaxy's current and future dynamical and chemical evolution.

Evolutionary Storage: Speeding up a Magnetic Disk by Clustering Frequent Data

To counteract the performance degradation in magnetic disks, it is proposed to develop an evolutionary storage system that is evolving over time. The frequent data is clustered and moved to a flash memory. A large disk trace, collected from real systems, has been used. The experimental results showed that the performance speedup due to the disk reorganization is 4.0

Multiple prefetch adaptive disk caching

A new disk caching algorithm is presented that uses an adaptive prefetching scheme to reduce the average service time for disk references. Unlike schemes which simply prefetch the next sector or group of sectors, this method maintains information about the order of past disk accesses which is used to accurately predict future access sequences. The range of parameters of this scheme is explored, and its performance is evaluated through trace-driven simulation, using traces obtained from three different UNIX minicomputers. Unlike disk trace data previously described in the literature, the traces used include time stamps for each reference. With this timing information-essential for evaluating any prefetching scheme-it is shown that a cache with the adaptive prefetching mechanism can reduce the average time to service a disk request by a factor of up to three, relative to an identical disk cache without prefetching.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Floral Anatomy in Gesneriaceae. I. Cyrtandroideae

The vascular anatomy of the flower of many cultivated species of this subfamily is surveyed, with emphasis on the nature of the vascular supply to the perianth parts, androecium, carpels, and nectariferous annular disk. Such a disk is absent in a number of taxa, and when present is not always vascularized. In three tribes the vascularized disk is supplied by a branch (disk trace) from each of five disk-stamen traces. In the Klugieae the disk is otherwise supplied, and this tribe stands apart in other respects. With certain exceptions (Klugieae, two species of Didymocarpeae), each of the two carpels is provided with a dorsal bundle, two ventral bundles, and two lateral bundles. The lateral bundles of adjacent carpels are always fused, and their ventral bundles are usually fused. The carpel ventrals and laterals arise from two ventrallateral mother strands, one on either side of the position of the loculus.